© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7782
    Prev
    Next
    INDEX
    Explanations

    mentions of notable sports figures and their performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    punctuation marks and numerical dates/scores in sports articles.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.68
     OMITBAD
    -0.68
     informée
    -0.61
    webElementXpaths
    -0.60
    IsMutable
    -0.59
     تكبرها
    -0.58
     ModelExpression
    -0.58
    IBOutlet
    -0.57
    MemoryWarning
    -0.56
    PyExc
    -0.56
    POSITIVE LOGITS
     youngster
    0.48
     veteran
    0.47
     newcomer
    0.44
     rookie
    0.43
     Josh
    0.43
     rookies
    0.40
     vété
    0.40
     veterans
    0.40
    Veteran
    0.39
     substitute
    0.38
    Activations Density 0.147%

    No Known Activations